coursera-transcripts 0.1.0__tar.gz

coursera_transcripts-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Kavin
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

coursera_transcripts-0.1.0/PKG-INFO

@@ -0,0 +1,150 @@
+Metadata-Version: 2.4
+Name: coursera-transcripts
+Version: 0.1.0
+Summary: CLI tool to extract Coursera course transcripts/subtitles
+Author-email: Kavin <your-email@example.com>
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Environment :: Console
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.31.0
+Requires-Dist: rich>=13.0.0
+Dynamic: license-file
+
+# 📚 Coursera Transcript Generator
+
+A beautiful CLI tool to bulk-download transcripts and subtitles from any Coursera course you're enrolled in.
+
+![CLI Preview](./preview.png)
+
+![Python](https://img.shields.io/badge/Python-3.10+-3776AB?logo=python&logoColor=white)
+![License](https://img.shields.io/badge/License-MIT-brightgreen)
+
+---
+
+## ✨ Features
+
+- **Interactive prompts** — guided step-by-step experience, no need to memorize flags
+- **Bulk download** — grabs every lecture transcript in a course at once
+- **Organized output** — files are neatly sorted into module folders
+- **Progress tracking** — real-time progress bar with download status
+- **Retry logic** — automatic retries with exponential backoff on failures
+- **Multiple formats** — supports both `.txt` (plain text) and `.srt` (subtitle) formats
+- **Multi-language** — download transcripts in any available language
+
+---
+
+## 📦 Installation
+
+```bash
+# Clone the repo
+git clone https://github.com/your-username/coursera-transcript-generator.git
+cd coursera-transcript-generator
+
+# Install in editable mode
+pip install -e .
+```
+
+---
+
+## 🚀 Usage
+
+### Interactive Mode (recommended)
+
+Just run the command with no arguments — it will guide you through everything:
+
+```bash
+coursera-transcripts
+```
+
+You'll be prompted for:
+
+1. **CAUTH cookie** — your Coursera authentication token
+2. **Course slug** — the identifier from the course URL
+3. **Options** — language, format, and output directory
+
+### CLI Mode
+
+Pass everything as flags for scripting / automation:
+
+```bash
+coursera-transcripts \
+  --cookie "YOUR_CAUTH_VALUE" \
+  --slug "machine-learning" \
+  --language en \
+  --format txt \
+  --output ./transcripts
+```
+
+### All Options
+
+| Flag         | Short | Default      | Description                    |
+| ------------ | ----- | ------------ | ------------------------------ |
+| `--cookie`   | `-c`  | _(prompted)_ | CAUTH cookie value             |
+| `--slug`     | `-s`  | _(prompted)_ | Course slug from URL           |
+| `--language` | `-l`  | `en`         | Subtitle language code         |
+| `--format`   |       | `txt`        | Output format (`txt` or `srt`) |
+| `--output`   | `-o`  | `./output`   | Parent output directory        |
+
+---
+
+## 🔑 Getting Your CAUTH Cookie
+
+1. Open [coursera.org](https://www.coursera.org) and **log in**
+2. Open **DevTools** (`F12` or `Ctrl+Shift+I`)
+3. Go to **Application** → **Cookies** → `https://www.coursera.org`
+4. Find the cookie named **`CAUTH`**
+5. Copy its **Value**
+
+> [!IMPORTANT]
+> You must be **enrolled** in the course to download its transcripts.
+
+---
+
+## 📁 Output Structure
+
+Transcripts are organized by module:
+
+```
+output/
+└── machine-learning/
+    ├── introduction-to-ml/
+    │   ├── Welcome to Machine Learning.txt
+    │   ├── What is Machine Learning.txt
+    │   └── Supervised Learning.txt
+    ├── linear-regression/
+    │   ├── Model Representation.txt
+    │   └── Cost Function.txt
+    └── ...
+```
+
+---
+
+## 🔧 Finding the Course Slug
+
+The slug is the part of the URL after `/learn/`:
+
+```
+https://www.coursera.org/learn/machine-learning
+                                └── this is the slug
+```
+
+---
+
+## 📋 Requirements
+
+- Python **3.10+**
+- A Coursera account with enrollment in the target course
+
+---
+
+## 📄 License
+
+MIT

coursera_transcripts-0.1.0/README.md

@@ -0,0 +1,130 @@
+# 📚 Coursera Transcript Generator
+
+A beautiful CLI tool to bulk-download transcripts and subtitles from any Coursera course you're enrolled in.
+
+![CLI Preview](./preview.png)
+
+![Python](https://img.shields.io/badge/Python-3.10+-3776AB?logo=python&logoColor=white)
+![License](https://img.shields.io/badge/License-MIT-brightgreen)
+
+---
+
+## ✨ Features
+
+- **Interactive prompts** — guided step-by-step experience, no need to memorize flags
+- **Bulk download** — grabs every lecture transcript in a course at once
+- **Organized output** — files are neatly sorted into module folders
+- **Progress tracking** — real-time progress bar with download status
+- **Retry logic** — automatic retries with exponential backoff on failures
+- **Multiple formats** — supports both `.txt` (plain text) and `.srt` (subtitle) formats
+- **Multi-language** — download transcripts in any available language
+
+---
+
+## 📦 Installation
+
+```bash
+# Clone the repo
+git clone https://github.com/your-username/coursera-transcript-generator.git
+cd coursera-transcript-generator
+
+# Install in editable mode
+pip install -e .
+```
+
+---
+
+## 🚀 Usage
+
+### Interactive Mode (recommended)
+
+Just run the command with no arguments — it will guide you through everything:
+
+```bash
+coursera-transcripts
+```
+
+You'll be prompted for:
+
+1. **CAUTH cookie** — your Coursera authentication token
+2. **Course slug** — the identifier from the course URL
+3. **Options** — language, format, and output directory
+
+### CLI Mode
+
+Pass everything as flags for scripting / automation:
+
+```bash
+coursera-transcripts \
+  --cookie "YOUR_CAUTH_VALUE" \
+  --slug "machine-learning" \
+  --language en \
+  --format txt \
+  --output ./transcripts
+```
+
+### All Options
+
+| Flag         | Short | Default      | Description                    |
+| ------------ | ----- | ------------ | ------------------------------ |
+| `--cookie`   | `-c`  | _(prompted)_ | CAUTH cookie value             |
+| `--slug`     | `-s`  | _(prompted)_ | Course slug from URL           |
+| `--language` | `-l`  | `en`         | Subtitle language code         |
+| `--format`   |       | `txt`        | Output format (`txt` or `srt`) |
+| `--output`   | `-o`  | `./output`   | Parent output directory        |
+
+---
+
+## 🔑 Getting Your CAUTH Cookie
+
+1. Open [coursera.org](https://www.coursera.org) and **log in**
+2. Open **DevTools** (`F12` or `Ctrl+Shift+I`)
+3. Go to **Application** → **Cookies** → `https://www.coursera.org`
+4. Find the cookie named **`CAUTH`**
+5. Copy its **Value**
+
+> [!IMPORTANT]
+> You must be **enrolled** in the course to download its transcripts.
+
+---
+
+## 📁 Output Structure
+
+Transcripts are organized by module:
+
+```
+output/
+└── machine-learning/
+    ├── introduction-to-ml/
+    │   ├── Welcome to Machine Learning.txt
+    │   ├── What is Machine Learning.txt
+    │   └── Supervised Learning.txt
+    ├── linear-regression/
+    │   ├── Model Representation.txt
+    │   └── Cost Function.txt
+    └── ...
+```
+
+---
+
+## 🔧 Finding the Course Slug
+
+The slug is the part of the URL after `/learn/`:
+
+```
+https://www.coursera.org/learn/machine-learning
+                                └── this is the slug
+```
+
+---
+
+## 📋 Requirements
+
+- Python **3.10+**
+- A Coursera account with enrollment in the target course
+
+---
+
+## 📄 License
+
+MIT

coursera_transcripts-0.1.0/pyproject.toml

@@ -0,0 +1,30 @@
+[project]
+name = "coursera-transcripts"
+version = "0.1.0"
+description = "CLI tool to extract Coursera course transcripts/subtitles"
+readme = "README.md"
+authors = [
+  { name="Kavin", email="your-email@example.com" }
+]
+license = { text = "MIT" }
+requires-python = ">=3.10"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Environment :: Console",
+]
+dependencies = [
+    "requests>=2.31.0",
+    "rich>=13.0.0",
+]
+
+[project.scripts]
+coursera-transcripts = "coursera_transcripts.cli:main"
+
+[build-system]
+requires = ["setuptools>=68.0"]
+build-backend = "setuptools.build_meta"

coursera_transcripts-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

coursera_transcripts-0.1.0/src/coursera_transcripts/api.py

@@ -0,0 +1,85 @@
+import time
+import requests
+from urllib.parse import urljoin
+
+from rich.console import Console
+
+
+COURSERA_BASE = "https://www.coursera.org"
+COURSERA_VERSION = "e184c443bbe09b70cbcebf2ba22b3b1067d7e119"
+
+HEADERS = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:149.0) Gecko/20100101 Firefox/149.0",
+    "Accept": "*/*",
+    "Accept-Language": "en",
+    "X-Coursera-Application": "ondemand",
+    "X-Coursera-Version": COURSERA_VERSION,
+    "X-Requested-With": "XMLHttpRequest",
+}
+
+
+def _build_headers(cookie: str, referer: str | None = None) -> dict:
+    headers = HEADERS.copy()
+    headers["Cookie"] = cookie
+    if referer:
+        headers["Referer"] = referer
+    return headers
+
+
+class CourseAPI:
+    def __init__(self, cookie: str, console: Console | None = None):
+        self.cookie = cookie
+        self.session = requests.Session()
+        self.console = console or Console()
+
+    def _get(self, url: str, referer: str | None = None, max_retries: int = 3) -> requests.Response:
+        headers = _build_headers(self.cookie, referer)
+        last_exception: Exception | None = None
+        for attempt in range(max_retries):
+            try:
+                response = self.session.get(url, headers=headers, timeout=30)
+                response.raise_for_status()
+                return response
+            except requests.exceptions.RequestException as e:
+                last_exception = e
+                if attempt == max_retries - 1:
+                    break
+                wait = 2 ** attempt
+                self.console.print(
+                    f"  [warning]⟳  Request failed, retrying in {wait}s…[/warning] [muted]({e})[/muted]"
+                )
+                time.sleep(wait)
+        raise last_exception  # type: ignore[misc]
+
+    def get_course_materials(self, slug: str) -> dict:
+        url = (
+            f"{COURSERA_BASE}/api/onDemandCourseMaterials.v2/"
+            f"?q=slug&slug={slug}"
+            f"&includes=modules%2Clessons%2CpassableItemGroups%2CpassableItemGroupChoices%2CpassableLessonElements%2Citems%2Ctracks%2CgradePolicy%2CgradingParameters%2CembeddedContentMapping"
+            f"&fields=moduleIds%2ConDemandCourseMaterialModules.v1(name%2Cslug%2Cdescription%2CtimeCommitment%2ClessonIds%2Coptional%2ClearningObjectives)%2ConDemandCourseMaterialLessons.v1(name%2Cslug%2CtimeCommitment%2CelementIds%2Coptional%2CtrackId)%2ConDemandCourseMaterialPassableItemGroups.v1(requiredPassedCount%2CpassableItemGroupChoiceIds%2CtrackId)%2ConDemandCourseMaterialPassableItemGroupChoices.v1(name%2Cdescription%2CitemIds)%2ConDemandCourseMaterialPassableLessonElements.v1(gradingWeight%2CisRequiredForPassing)%2ConDemandCourseMaterialItems.v2(name%2CoriginalName%2Cslug%2CtimeCommitment%2CcontentSummary%2CisLocked%2ClockableByItem%2CitemLockedReasonCode%2CtrackId%2ClockedStatus%2CitemLockSummary%2CcustomDisplayTypenameOverride)%2ConDemandCourseMaterialTracks.v1(passablesCount)%2ConDemandGradingParameters.v1(gradedAssignmentGroups)%2CcontentAtomRelations.v1(embeddedContentSourceCourseId%2CsubContainerId)"
+            f"&showLockedItems=true"
+        )
+        referer = f"{COURSERA_BASE}/learn/{slug}/home/module/1"
+        response = self._get(url, referer)
+        data = response.json()
+
+        if not data.get("elements"):
+            raise ValueError(f"Course '{slug}' not found or no data returned")
+
+        return data
+
+    def get_lecture_video(self, course_id: str, item_id: str) -> dict:
+        url = (
+            f"{COURSERA_BASE}/api/onDemandLectureVideos.v1/"
+            f"{course_id}~{item_id}"
+            f"?includes=video"
+            f"&fields=onDemandVideos.v1(sources%2Csubtitles%2CsubtitlesTxt%2CsubtitlesAssetTags%2CdubbedSources%2CdubbedSubtitlesVtt%2CaudioDescriptionVideoSources)"
+            f"%2CdisableSkippingForward%2CstartMs%2CendMs"
+        )
+        response = self._get(url)
+        return response.json()
+
+    def download_subtitle(self, relative_url: str) -> str:
+        url = urljoin(COURSERA_BASE, relative_url)
+        response = self._get(url)
+        return response.text

coursera_transcripts-0.1.0/src/coursera_transcripts/cli.py

@@ -0,0 +1,200 @@
+import argparse
+import sys
+from pathlib import Path
+
+from rich.console import Console
+from rich.panel import Panel
+from rich.prompt import Prompt
+from rich.text import Text
+from rich.theme import Theme
+
+from .api import CourseAPI
+from .downloader import TranscriptDownloader
+
+# ── Custom theme ──────────────────────────────────────────────────────
+custom_theme = Theme({
+    "brand":    "bold bright_cyan",
+    "accent":   "bright_magenta",
+    "success":  "bold bright_green",
+    "warning":  "bold yellow",
+    "error":    "bold red",
+    "muted":    "dim white",
+    "info":     "bright_blue",
+})
+
+console = Console(theme=custom_theme)
+
+BANNER = r"""[bright_cyan]
+   ██████╗ ██████╗ ██╗   ██╗██████╗ ███████╗███████╗██████╗  █████╗
+  ██╔════╝██╔═══██╗██║   ██║██╔══██╗██╔════╝██╔════╝██╔══██╗██╔══██╗
+  ██║     ██║   ██║██║   ██║██████╔╝███████╗█████╗  ██████╔╝███████║
+  ██║     ██║   ██║██║   ██║██╔══██╗╚════██║██╔══╝  ██╔══██╗██╔══██║
+  ╚██████╗╚██████╔╝╚██████╔╝██║  ██║███████║███████╗██║  ██║██║  ██║
+   ╚═════╝ ╚═════╝  ╚═════╝ ╚═╝  ╚═╝╚══════╝╚══════╝╚═╝  ╚═╝╚═╝  ╚═╝
+[/bright_cyan]"""
+
+
+def _show_banner() -> None:
+    console.print(BANNER)
+    subtitle = Text("Transcript Generator", style="bold bright_magenta")
+    subtitle.append("  •  ", style="dim")
+    subtitle.append("v0.1.0", style="dim bright_cyan")
+    console.print(subtitle, justify="center")
+    console.print()
+
+
+def _normalize_cookie(raw: str) -> str:
+    """Accept a raw CAUTH token, CAUTH=value, or a full Cookie header string."""
+    raw = raw.strip()
+    if "CAUTH=" in raw:
+        # Already contains the CAUTH key — treat as a full cookie string
+        return raw
+    # Bare token value — wrap it
+    return f"CAUTH={raw}"
+
+
+def _prompt_cookie() -> str:
+    console.print(
+        Panel(
+            "[muted]Paste your [bold bright_cyan]Cookie[/bold bright_cyan] header or just the [bold bright_cyan]CAUTH[/bold bright_cyan] value.\n"
+            "You can copy the full Cookie header from DevTools → Network → any request → Headers.[/muted]",
+            title="[brand]🔑  Authentication[/brand]",
+            border_style="bright_cyan",
+            padding=(1, 2),
+        )
+    )
+    cookie = Prompt.ask("[bright_cyan]  ›[/bright_cyan] [bold]Cookie / CAUTH[/bold]")
+    if not cookie.strip():
+        console.print("[error]  ✖  Cookie cannot be empty.[/error]")
+        raise SystemExit(1)
+    return _normalize_cookie(cookie)
+
+
+def _prompt_slug() -> str:
+    console.print()
+    console.print(
+        Panel(
+            "[muted]Enter the course slug from the URL.\n"
+            "Example: [bold bright_cyan]coursera.org/learn/[underline]unreal-engine-fundamentals[/underline][/bold bright_cyan][/muted]",
+            title="[brand]📚  Course[/brand]",
+            border_style="bright_cyan",
+            padding=(1, 2),
+        )
+    )
+    slug = Prompt.ask("[bright_cyan]  ›[/bright_cyan] [bold]Course slug[/bold]")
+    if not slug.strip():
+        console.print("[error]  ✖  Slug cannot be empty.[/error]")
+        raise SystemExit(1)
+    return slug.strip()
+
+
+def _prompt_options() -> tuple[str, str, Path]:
+    console.print()
+    console.print(
+        Panel(
+            "[muted]Configure optional settings (press Enter for defaults).[/muted]",
+            title="[brand]⚙  Options[/brand]",
+            border_style="bright_cyan",
+            padding=(1, 2),
+        )
+    )
+    language = Prompt.ask(
+        "[bright_cyan]  ›[/bright_cyan] [bold]Language[/bold]",
+        default="en",
+    )
+    fmt = Prompt.ask(
+        "[bright_cyan]  ›[/bright_cyan] [bold]Format[/bold] [muted](srt/txt)[/muted]",
+        choices=["srt", "txt"],
+        default="txt",
+    )
+    output = Prompt.ask(
+        "[bright_cyan]  ›[/bright_cyan] [bold]Output directory[/bold]",
+        default="./output",
+    )
+    return language, fmt, Path(output).resolve()
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description="Download transcripts/subtitles from a Coursera course",
+    )
+    parser.add_argument(
+        "--cookie", "-c",
+        help="Coursera authentication cookie (CAUTH value). If omitted, you will be prompted.",
+    )
+    parser.add_argument(
+        "--slug", "-s",
+        help="Course slug (e.g. 'unreal-engine-fundamentals'). If omitted, you will be prompted.",
+    )
+    parser.add_argument(
+        "--output", "-o",
+        default=None,
+        help="Parent output directory (default: ./output). Transcripts saved to {output}/{slug}/",
+    )
+    parser.add_argument(
+        "--language", "-l",
+        default=None,
+        help="Subtitle language code (default: en)",
+    )
+    parser.add_argument(
+        "--format",
+        choices=["srt", "txt"],
+        default=None,
+        help="Subtitle format (default: txt)",
+    )
+    return parser.parse_args()
+
+
+def main():
+    args = parse_args()
+
+    # ── Interactive mode when cookie/slug not provided ────────────────
+    interactive = args.cookie is None or args.slug is None
+
+    if interactive:
+        _show_banner()
+
+    # Cookie
+    if args.cookie:
+        cookie = _normalize_cookie(args.cookie)
+    else:
+        cookie = _prompt_cookie()
+
+    # Slug
+    slug = args.slug if args.slug else _prompt_slug()
+
+    # Options
+    if interactive and (args.language is None and args.format is None and args.output is None):
+        language, fmt, output_dir = _prompt_options()
+    else:
+        language = args.language or "en"
+        fmt = args.format or "txt"
+        output_dir = Path(args.output or "./output").resolve()
+
+    console.print()
+
+    # ── Run ───────────────────────────────────────────────────────────
+    api = CourseAPI(cookie, console)
+    downloader = TranscriptDownloader(
+        api=api,
+        output_dir=output_dir,
+        language=language,
+        fmt=fmt,
+        console=console,
+    )
+
+    try:
+        downloader.fetch_all_transcripts(slug)
+    except ValueError as e:
+        console.print(f"\n[error]  ✖  {e}[/error]")
+        raise SystemExit(1)
+    except KeyboardInterrupt:
+        console.print("\n[warning]  ⚠  Interrupted by user.[/warning]")
+        raise SystemExit(130)
+    except Exception as e:
+        console.print(f"\n[error]  ✖  Unexpected error: {e}[/error]")
+        raise SystemExit(1)
+
+
+if __name__ == "__main__":
+    main()

coursera_transcripts-0.1.0/src/coursera_transcripts/downloader.py

@@ -0,0 +1,238 @@
+import re
+import time
+from pathlib import Path
+
+from rich.console import Console
+from rich.panel import Panel
+from rich.progress import (
+    Progress,
+    SpinnerColumn,
+    TextColumn,
+    BarColumn,
+    MofNCompleteColumn,
+    TimeElapsedColumn,
+)
+from rich.table import Table
+from rich.text import Text
+from rich.tree import Tree
+
+from .api import CourseAPI
+
+
+def _sanitize_filename(name: str) -> str:
+    name = re.sub(r'[<>:"/\\|?*]', '', name)
+    name = name.strip()
+    name = name[:200]
+    return name
+
+
+def _extract_course_id(materials_data: dict) -> str:
+    return materials_data["elements"][0]["id"]
+
+
+def _build_module_lookup(materials_data: dict) -> dict:
+    lookup = {}
+    for module in materials_data.get("linked", {}).get("onDemandCourseMaterialModules.v1", []):
+        lookup[module["id"]] = {
+            "name": module["name"],
+            "slug": module.get("slug", module["id"]),
+        }
+    return lookup
+
+
+def _build_lesson_lookup(materials_data: dict) -> dict:
+    lookup = {}
+    for lesson in materials_data.get("linked", {}).get("onDemandCourseMaterialLessons.v1", []):
+        lookup[lesson["id"]] = {
+            "name": lesson["name"],
+            "slug": lesson.get("slug", lesson["id"]),
+        }
+    return lookup
+
+
+def _get_lecture_items(materials_data: dict) -> list:
+    items = materials_data.get("linked", {}).get("onDemandCourseMaterialItems.v2", [])
+    lectures = []
+    for item in items:
+        content_type = item.get("contentSummary", {}).get("typeName", "")
+        if content_type != "lecture":
+            continue
+        if item.get("isLocked", False):
+            continue
+        lectures.append(item)
+    return lectures
+
+
+class TranscriptDownloader:
+    def __init__(
+        self,
+        api: CourseAPI,
+        output_dir: Path,
+        language: str = "en",
+        fmt: str = "txt",
+        console: Console | None = None,
+    ):
+        self.api = api
+        self.output_dir = output_dir
+        self.language = language
+        self.fmt = fmt
+        self.console = console or Console()
+
+    def _get_subtitle_url(self, video_data: dict) -> str | None:
+        videos = video_data.get("linked", {}).get("onDemandVideos.v1", [])
+        if not videos:
+            return None
+
+        video = videos[0]
+
+        if self.fmt == "txt":
+            subtitles = video.get("subtitlesTxt", {})
+        else:
+            subtitles = video.get("subtitles", {})
+
+        return subtitles.get(self.language)
+
+    def fetch_all_transcripts(self, course_slug: str) -> dict:
+        c = self.console
+
+        # ── Fetch course data ─────────────────────────────────────────
+        with c.status("[bright_cyan]  Fetching course materials…[/bright_cyan]", spinner="dots"):
+            materials = self.api.get_course_materials(course_slug)
+
+        course_id = _extract_course_id(materials)
+        module_lookup = _build_module_lookup(materials)
+        lesson_lookup = _build_lesson_lookup(materials)
+        lecture_items = _get_lecture_items(materials)
+
+        course_dir = self.output_dir / course_slug
+        course_dir.mkdir(parents=True, exist_ok=True)
+
+        # ── Course overview panel ─────────────────────────────────────
+        info_table = Table.grid(padding=(0, 2))
+        info_table.add_column(style="muted", justify="right")
+        info_table.add_column(style="bold white")
+        info_table.add_row("Course", course_slug)
+        info_table.add_row("Lectures", str(len(lecture_items)))
+        info_table.add_row("Language", self.language.upper())
+        info_table.add_row("Format", self.fmt.upper())
+        info_table.add_row("Output", str(course_dir))
+
+        c.print(
+            Panel(
+                info_table,
+                title="[brand]📋  Course Overview[/brand]",
+                border_style="bright_cyan",
+                padding=(1, 2),
+            )
+        )
+        c.print()
+
+        if not lecture_items:
+            c.print("[warning]  ⚠  No lecture videos found in this course.[/warning]")
+            return {"success": 0, "skipped": 0, "failed": 0, "total": 0}
+
+        # ── Download with progress bar ────────────────────────────────
+        stats = {"success": 0, "skipped": 0, "failed": 0, "total": len(lecture_items)}
+        results: list[tuple[str, str, str]] = []  # (status_icon, name, detail)
+
+        with Progress(
+            SpinnerColumn(style="bright_cyan"),
+            TextColumn("[bold]{task.description}[/bold]"),
+            BarColumn(
+                bar_width=30,
+                style="dim white",
+                complete_style="bright_cyan",
+                finished_style="bright_green",
+            ),
+            MofNCompleteColumn(),
+            TextColumn("•"),
+            TimeElapsedColumn(),
+            console=c,
+            transient=False,
+        ) as progress:
+            task = progress.add_task("  Downloading transcripts", total=stats["total"])
+
+            for idx, item in enumerate(lecture_items, 1):
+                item_id = item["id"]
+                item_name = _sanitize_filename(item["name"])
+                module_id = item.get("moduleId", "")
+
+                module_info = module_lookup.get(module_id, {})
+                module_slug = module_info.get("slug", f"module-{module_id}")
+
+                module_dir = course_dir / module_slug
+                module_dir.mkdir(parents=True, exist_ok=True)
+
+                # Fetch video data
+                try:
+                    video_data = self.api.get_lecture_video(course_id, item_id)
+                except Exception as e:
+                    results.append(("❌", item_name, f"[error]Failed to fetch video data: {e}[/error]"))
+                    stats["failed"] += 1
+                    progress.advance(task)
+                    continue
+
+                subtitle_url = self._get_subtitle_url(video_data)
+
+                if not subtitle_url:
+                    results.append(("⊘", item_name, f"[warning]No {self.language} {self.fmt} subtitles[/warning]"))
+                    stats["skipped"] += 1
+                    progress.advance(task)
+                    continue
+
+                # Download subtitle
+                try:
+                    subtitle_text = self.api.download_subtitle(subtitle_url)
+                except Exception as e:
+                    results.append(("❌", item_name, f"[error]Download failed: {e}[/error]"))
+                    stats["failed"] += 1
+                    progress.advance(task)
+                    continue
+
+                filename = f"{item_name}.{self.fmt}"
+                filepath = module_dir / filename
+                filepath.write_text(subtitle_text, encoding="utf-8")
+
+                rel_path = filepath.relative_to(self.output_dir)
+                results.append(("✔", item_name, f"[muted]{rel_path}[/muted]"))
+                stats["success"] += 1
+                progress.advance(task)
+
+        # ── Results tree ──────────────────────────────────────────────
+        c.print()
+
+        tree = Tree("[bold bright_cyan]📂  Results[/bold bright_cyan]")
+        for icon, name, detail in results:
+            if icon == "✔":
+                style_icon = f"[bright_green]{icon}[/bright_green]"
+            elif icon == "⊘":
+                style_icon = f"[yellow]{icon}[/yellow]"
+            else:
+                style_icon = f"[red]{icon}[/red]"
+            tree.add(f"{style_icon}  [bold]{name}[/bold]  {detail}")
+        c.print(tree)
+
+        # ── Summary panel ─────────────────────────────────────────────
+        c.print()
+
+        summary_parts = []
+        if stats["success"]:
+            summary_parts.append(f"[bright_green]✔ {stats['success']} downloaded[/bright_green]")
+        if stats["skipped"]:
+            summary_parts.append(f"[yellow]⊘ {stats['skipped']} skipped[/yellow]")
+        if stats["failed"]:
+            summary_parts.append(f"[red]✖ {stats['failed']} failed[/red]")
+
+        summary_text = "   ".join(summary_parts)
+        summary_text += f"\n\n[muted]Files saved to [bold]{course_dir}[/bold][/muted]"
+
+        c.print(
+            Panel(
+                summary_text,
+                title="[brand]✨  Summary[/brand]",
+                border_style="bright_green" if not stats["failed"] else "yellow",
+                padding=(1, 2),
+            )
+        )
+
+        return stats

coursera_transcripts-0.1.0/src/coursera_transcripts.egg-info/PKG-INFO

@@ -0,0 +1,150 @@
+Metadata-Version: 2.4
+Name: coursera-transcripts
+Version: 0.1.0
+Summary: CLI tool to extract Coursera course transcripts/subtitles
+Author-email: Kavin <your-email@example.com>
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Environment :: Console
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.31.0
+Requires-Dist: rich>=13.0.0
+Dynamic: license-file
+
+# 📚 Coursera Transcript Generator
+
+A beautiful CLI tool to bulk-download transcripts and subtitles from any Coursera course you're enrolled in.
+
+![CLI Preview](./preview.png)
+
+![Python](https://img.shields.io/badge/Python-3.10+-3776AB?logo=python&logoColor=white)
+![License](https://img.shields.io/badge/License-MIT-brightgreen)
+
+---
+
+## ✨ Features
+
+- **Interactive prompts** — guided step-by-step experience, no need to memorize flags
+- **Bulk download** — grabs every lecture transcript in a course at once
+- **Organized output** — files are neatly sorted into module folders
+- **Progress tracking** — real-time progress bar with download status
+- **Retry logic** — automatic retries with exponential backoff on failures
+- **Multiple formats** — supports both `.txt` (plain text) and `.srt` (subtitle) formats
+- **Multi-language** — download transcripts in any available language
+
+---
+
+## 📦 Installation
+
+```bash
+# Clone the repo
+git clone https://github.com/your-username/coursera-transcript-generator.git
+cd coursera-transcript-generator
+
+# Install in editable mode
+pip install -e .
+```
+
+---
+
+## 🚀 Usage
+
+### Interactive Mode (recommended)
+
+Just run the command with no arguments — it will guide you through everything:
+
+```bash
+coursera-transcripts
+```
+
+You'll be prompted for:
+
+1. **CAUTH cookie** — your Coursera authentication token
+2. **Course slug** — the identifier from the course URL
+3. **Options** — language, format, and output directory
+
+### CLI Mode
+
+Pass everything as flags for scripting / automation:
+
+```bash
+coursera-transcripts \
+  --cookie "YOUR_CAUTH_VALUE" \
+  --slug "machine-learning" \
+  --language en \
+  --format txt \
+  --output ./transcripts
+```
+
+### All Options
+
+| Flag         | Short | Default      | Description                    |
+| ------------ | ----- | ------------ | ------------------------------ |
+| `--cookie`   | `-c`  | _(prompted)_ | CAUTH cookie value             |
+| `--slug`     | `-s`  | _(prompted)_ | Course slug from URL           |
+| `--language` | `-l`  | `en`         | Subtitle language code         |
+| `--format`   |       | `txt`        | Output format (`txt` or `srt`) |
+| `--output`   | `-o`  | `./output`   | Parent output directory        |
+
+---
+
+## 🔑 Getting Your CAUTH Cookie
+
+1. Open [coursera.org](https://www.coursera.org) and **log in**
+2. Open **DevTools** (`F12` or `Ctrl+Shift+I`)
+3. Go to **Application** → **Cookies** → `https://www.coursera.org`
+4. Find the cookie named **`CAUTH`**
+5. Copy its **Value**
+
+> [!IMPORTANT]
+> You must be **enrolled** in the course to download its transcripts.
+
+---
+
+## 📁 Output Structure
+
+Transcripts are organized by module:
+
+```
+output/
+└── machine-learning/
+    ├── introduction-to-ml/
+    │   ├── Welcome to Machine Learning.txt
+    │   ├── What is Machine Learning.txt
+    │   └── Supervised Learning.txt
+    ├── linear-regression/
+    │   ├── Model Representation.txt
+    │   └── Cost Function.txt
+    └── ...
+```
+
+---
+
+## 🔧 Finding the Course Slug
+
+The slug is the part of the URL after `/learn/`:
+
+```
+https://www.coursera.org/learn/machine-learning
+                                └── this is the slug
+```
+
+---
+
+## 📋 Requirements
+
+- Python **3.10+**
+- A Coursera account with enrollment in the target course
+
+---
+
+## 📄 License
+
+MIT

coursera_transcripts-0.1.0/src/coursera_transcripts.egg-info/SOURCES.txt

@@ -0,0 +1,13 @@
+LICENSE
+README.md
+pyproject.toml
+src/coursera_transcripts/__init__.py
+src/coursera_transcripts/api.py
+src/coursera_transcripts/cli.py
+src/coursera_transcripts/downloader.py
+src/coursera_transcripts.egg-info/PKG-INFO
+src/coursera_transcripts.egg-info/SOURCES.txt
+src/coursera_transcripts.egg-info/dependency_links.txt
+src/coursera_transcripts.egg-info/entry_points.txt
+src/coursera_transcripts.egg-info/requires.txt
+src/coursera_transcripts.egg-info/top_level.txt

coursera_transcripts-0.1.0/src/coursera_transcripts.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

coursera_transcripts-0.1.0/src/coursera_transcripts.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+coursera-transcripts = coursera_transcripts.cli:main

coursera_transcripts-0.1.0/src/coursera_transcripts.egg-info/requires.txt

@@ -0,0 +1,2 @@
+requests>=2.31.0
+rich>=13.0.0

coursera_transcripts-0.1.0/src/coursera_transcripts.egg-info/top_level.txt

@@ -0,0 +1 @@
+coursera_transcripts